个人信息
Personal Information
联系方式
Contact Information
个人简介
Personal Profile
廖振宇,于法国巴黎萨克雷大学获信号与图像处理硕士和计算机博士学位,后在美国加州大学伯克利分校从事博士后研究工作,于2021年起至今在华中科技大学电信学院工作,任副研究员。
长期从事“面向高维数据的大规模机器学习的基础理论和关键技术”的研究,将高维统计学和随机矩阵理论应用于复杂大规模机器学习系统设计,以解决非监督学习、神经网络优化设计、压缩和加速问题,成果发表在ICML、NeurIPS、ICLR、COLT、AISTATS、TSP、AAP、JSTAT等人工智能、机器学习顶级会议与期刊,合著专著Random Matrix Methods for Machine Learning,被美国科学院院士Gérard Ben Arous在封底简评中评价为“very well-organized and carefully written book by two leading experts”。长期受邀担任多个人工智能、机器学习领域顶级会议和期刊的审稿人或程序委员会委员,受邀担任欧盟自然科学基金ERC和加拿大自然科学基金NSERC外部评审。
受邀为加拿大CRM-Simons访问教授、法国ANR-CIMI访问教授,获湖北省青年人才计划、湖北省武汉英才、华中科技大学东湖青年学者和法国巴黎萨克雷大学ED STIC优秀博士论文。牵头或参与包括中国自然科学基金青年基金、重点专项,CCF-海康威视斑头雁基金, 广东省人工智能数理基础重点实验室开放基金、华为拉格朗日数学计算中心研究基金、法国和美国自然科学基金等一系列科研项目。
所在团队为队邱才明教授领导的华中科技大学电信学院“移动通信与智能系统实验室”。
团队包括6名教师,长期聚焦无线通信和人工智能中的基础理论、技术、标准和产业应用,布局下一代智能无线通信(6G)中的智能反射面和通信、感知、计算一体化技术。智能反射面通过可编程电磁单元调控电磁波传播,为无线传输环境的主动可控提供了有效手段;通感算一体化网络是指同时具备泛在智能通信、计算能力、泛在感知的网络。
在国家自然科学基金(重点)专项和一系列省部级重点研发项目的支持下,团队围绕智能反射面、通感算一体化网络和智能通信、人工智能理论和技术,在国际信息论旗舰杂志IEEE Transactions on Information Theory和NeurIPS、 ICML、ICLR等通信与人工智能领域的旗舰会议和期刊发表三十余篇,于剑桥大学出版社出版专著一部,夯实新一代移动通信和智能系统的数理基础,促进信息科学与数学的交叉发展,促进未来在短距通信、无人驾驶、智慧交通、边缘计算等千行百业中的广泛应用。
上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg2024-2026:广东省人工智能数理基础重点实验室开放基金:基于随机矩阵方法的 Transformer 模型泛化理论研 究(OFA00003),10 万元,主持
2023-2025:国家自然科学基金青年科学基金项目:基于随机矩阵方法的神经网络模型剪枝基础理论研究(NSFC-62206101),30 万元,主持
2023-2025:华为技术有限公司校企合作项目:随机矩阵理论驱动的通信理论和算法研究(TC20231122043), 59 万元,主持
2022-2025:国家自然科学基金“面向未来通信的数学基础(信息论)”专项项目:智能反射面辅助的新型无线通信数学理论与数学技术(NSFC-12141107),300 万元,核心成员
2021-2024:中国中央高校基本科研业务费专项资金资助(No. 2021XXJS110):高维随机矩阵方法在机器学习模型中的理论和应用,50 万元,主持
2021-2023 湖北省重点研发计划项目:新一代工业互联网网络关键技术研究(2021BAA037),100 万元,核心成员
2021-2022 中国计算机学会 CCF-海康威视斑头雁基金项目:基于随机矩阵和信息瓶颈理论的神经网络表达和压缩的研究(20210008),28 万元,主持
2021-2024 广西省重点研发计划项目:交通路网重要节点主动安全防控智能一体化成套技术研究与产业化(桂科 AB21196034),500 万元,核心成员
2018-2021 NSF Research Grant, Combining Stochastics and Numerics for Improved Scalable Matrix Computations (NSF-1815054),500k 美元,核心成员
2018-2021 法国高等教育、研究与创新部:GSTATS-IDEX DataScience Chair,300k 欧元,核心成员
2015-2017 法国自然科学基金委:Random Matrix Theory for Large Dimensional Graphs (ANR-14-CE28-0006),300k 欧元,核心成员
W. Yang, Z. Wang, X. Mai, Z. Ling, R. C. Qiu, Z. Liao “Inconsistency of ESPRIT DoA Estimation for Large Arrays and a Correction via RMT”, IEEE 32nd European Signal Processing Conference (EUSIPCO 2024), 2024.
Z. Ling, L. Li, Z. Feng, Y. Zhang, F. Zhou, R. C. Qiu, Z. Liao “Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures”, International Conference on Machine Learning (ICML 2024), 2024.
Y. Song, K. Wan, Z. Liao, H. Xu, G. Caire, S. Shamai, “An Achievable and Analytic Solution to Information Bottleneck for Gaussian Mixtures”, 2024 IEEE International Symposium on Information Theory (ISIT 2024), 2024.
Y. Wang, Z. Feng, Z. Liao, “FedRF-Adapt: Robust and Communication-Efficient Federated Domain Adaptation via Random Features”, Workshop on Timely and Private Machine Learning over Networks, 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024), 2024. slides
Y. Du, Z. Ling, R. C. Qiu, Z. Liao, “High-dimensional Learning Dynamics of Deep Neural Nets in the Neural Tangent Regime”, High-dimensional Learning Dynamics Workshop, The Fortieth International Conference on Machine Learning (ICML'2023), 2023.
Z. Ling, Z. Liao, R. C. Qiu, “On the Equivalence Between Implicit and Explicit Neural Networks: A High-dimensional Viewpoint”, High-dimensional Learning Dynamics Workshop, The Fortieth International Conference on Machine Learning (ICML'2023), 2023.
L. Gu, Y. Du, Y. Zhang, D. Xie, S. Pu, R. C. Qiu, Z. Liao, “ “Lossless” Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach”, The 36th Conference on Neural Information Processing Systems (NeurIPS'2022), 2022.
H. Tiomoko, Z. Liao, R. Couillet, “Random matrices in service of ML footprint: ternary random features with no performance loss”, The Tenth International Conference on Learning Representations (ICLR'2022), 2022.
Z. Liao, M. W. Mahoney, “Hessian Eigenspectra of More Realistic Nonlinear Models” (oral), The 35th Conference on Neural Information Processing Systems (NeurIPS'2021), 2021.
M. Dereziński, Z. Liao, E. Dobriban, M. W. Mahoney, “Sparse sketches with small inversion bias”, The 34th Annual Conference on Learning Theory (COLT'2021), 2021.
F. Liu, Z.Liao, J. A.K. Suykens, “Kernel regression in high dimension: Refined analysis beyond double descent”, The 24th International Conference on Artificial Intelligence and Statistics (AISTATS'2021), 2021.
Z.Liao, R. Couillet, M. W. Mahoney, “Sparse Quantized Spectral Clustering” (spotlight), The Ninth International Conference on Learning Representations (ICLR'2021), 2021.
Z.Liao, R. Couillet, M. W. Mahoney, “A Random Matrix Analysis of Random Fourier Features: Beyond the Gaussian Kernel, A Precise Phase Transition, and the Corresponding Double Descent”, The 34th Conference on Neural Information Processing Systems (NeurIPS'2020), Vancouver, Canada, 2020.
M. Dereziński, F. Liang, Z. Liao, M. W. Mahoney, “Precise expressions for random projections: Low-rank approximation and randomized Newton”, The 34th Conference on Neural Information Processing Systems (NeurIPS'2020), Vancouver, Canada, 2020.
X. Mai, Z. Liao, R. Couillet, “A Large Scale Analysis of Logistic Regression: Asymptotic Performance and New Insights”, 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'2019), Brighton, UK, 2019.
Z. Liao, R. Couillet, “On the Spectrum of Random Features Maps of High Dimensional Data”, Proceedings of the 35th International Conference on Machine Learning (ICML'2018), Stockholm, Sweden, 2018. (long talk)
Z. Liao, R. Couillet, “The Dynamics of Learning: A Random Matrix Approach”, Proceedings of the 35th International Conference on Machine Learning (ICML'2018), Stockholm, Sweden, 2018. (long talk)
Z. Liao, R. Couillet, “Random Matrices Meet Machine Learning: A Large Dimensional Analysis of LS-SVM”, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'2017), New Orleans, USA, 2017.
J. Wang, S. Zhang, J. Cai, Z. Liao, C. Arenz, R. Betzholz, “Robustness of random-control quantum-state tomography”, Physical Review A 108 (2 Aug. 2023), 022408.
Y. Chitour, Z. Liao, R. Couillet, “A geometric approach of gradient descent algorithms in linear neural networks”, Mathematical Control and Related Fields, 13(3) (2023), 918–945.
Z.Liao, R. Couillet, M. W. Mahoney, “A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent”, Journal of Statistical Mechanics: Theory and Experiment 2021(12) (Dec. 2021), 124006.
Z. Liao, R. Couillet, “A Large Dimensional Analysis of Least Squares Support Vector Machines”, IEEE Transactions on Signal Processing 67 (4) (Feb. 2019), 1065-1074. (University of Paris-Saclay ED STIC Ph.D. Paper Award)
C. Louart, Z. Liao, R. Couillet, “A Random Matrix Approach to Neural Networks”, The Annals of Applied Probability 28 (2) (Apr. 2018), 1190-1248.
文件上传中...